Abstract: A data cache server may process requests from a data cache client to put, get, and delete data items into or from the data cache server. Each data item may be based on data in a data store. In response to each request to put a data item into the data cache server, the data cache server may determine whether any of the data in the data store on which the data item is based has or may have changed; put the data item into the data cache memory if none of the data in the data store on which the data item is based has been determined to have or maybe to have changed, and not put the data item into the data cache memory if data in the data store on which the data item is based has been determined to have or maybe to have changed.

Abstract: An SQL query-to-procedure translation system may be used in connection with a relational database management system (RDBMS) that is augmented by a cache and a cache management system that manages the cache. The query-to-procedure translation system may include a data processing system that has at least one computer hardware processor and a configuration that, in response to a query issued by an application program for data from the relational database management system: intercepts the query; generates code that determines if data requested by the query that may be in the cache has changed; and registers the code as a procedure with the RDBMS.

Abstract: A data cache server may process requests from a data cache client to put, get, and delete data items into or from the data cache server. Each data item may be based on data in a data store. In response to each request to put a data item into the data cache server, the data cache server may determine whether any of the data in the data store on which the data item is based has or may have changed; put the data item into the data cache memory if none of the data in the data store on which the data item is based has been determined to have or maybe to have changed, and not put the data item into the data cache memory if data in the data store on which the data item is based has been determined to have or maybe to have changed.

Abstract: A single queue is utilized for scheduling of prioritized requests having specific deadlines in which to be serviced. New requests are initially inserted into the single queue based upon optimal SCAN order. Once the new request is inserted, the deadlines of all the requests in the queue are checked in order to insure each request deadline is met. In the event a deadline violation is identified, the queue is reorganized by identifying the lowest priority request currently to be processed prior to the request with the deadline violation. If more than one request with the lowest priority exists, the lowest priority request with the greatest deadline slack is selected. Ultimately, the selected request is moved to the tail of the queue, or removed from the queue and considered lost if its deadline is violated with a queue tail placement. This process is repeated until the queue is in a state with no deadline violations.

Abstract: The disk scheduling system supports the processing of simultaneous storage device read and write requests in a video server environment, thereby supporting both video-on-demand and non-linear editing applications. Read requests are the result of movie viewing, while write requests are the result of video clip editing or movie authoring procedures. Due to real-time demands of movie viewing, read requests have to be fulfilled within certain deadlines, otherwise they are considered lost. Since the data to be written into the storage device is stored in main memory buffers (or write buffers), write requests can be postponed until critical read requests are processed. However, write requests still have to be proceeded within reasonable delays and without the possibility of indefinite postponement. This is due to the physical constraint of the limited size of the main memory buffers.

Abstract: A multimedia object is declustered across a multiple of disk drives to employ the aggregate bandwidth of the several disk drives so that continuous retrieval or display of the object is achieved. The clusters are logically defined across a plurality of disk drives instead of being physically defined so that two consecutive subobjects comprising the data object may be on the same disks. The subobjects are assigned to the disks so that the first fragment of one subobject is k disks apart from the drive that contains the first fragment of the preceding subobject, where k is a fixed stride.